Solar Development Feasibility Assessment with Satellite Data

Evaluate large-scale solar sites before breaking ground. Klarety runs cloud-free Sentinel-2 NDVI analysis to measure vegetation cover, computes slope and aspect from elevation data, and streams a site-readiness report with terrain suitability scores. One prompt replaces weeks of manual GIS preprocessing.

Start your assessment

Satellite-based solar site screening workflow

Klarety AI

Site-readiness reports from one prompt

Klarety agents run NDVI, slope, and aspect analysis on any AOI and return a scored feasibility report instantly.

Sentinel-2 + DEM

Cloud-free NDVI and terrain slope analysis

Agents mosaic cloud-free imagery, compute vegetation and terrain indices, and flag unsuitable zones automatically.

GIS Output

GIS-ready slope and vegetation site layers

Export slope-aspect rasters and vegetation mask layers to your GIS for site engineering review and permitting workflows.

How Klarety scores solar site feasibility

Klarety agents mosaic cloud-free Sentinel-2 for NDVI vegetation density, compute slope and aspect from SRTM DEM at 30m, and score each grid cell on a 0-100 suitability index. Unsuitable zones (slope >5 degrees, high vegetation, protected land) are masked automatically. Output is a scored GeoTIFF and summary table, ready for site engineering review.

Klarety AIRun solar feasibility on your AOI

analysis/solar_feasibility_score.pyAgent code

python

import eeimport numpy as np
ee.Initialize()
# Example: Atacama Desert candidate siteaoi = ee.Geometry.Rectangle([-69.5, -23.8, -68.8, -23.2])
# Cloud-free Sentinel-2 median composites2 = (ee.ImageCollection('COPERNICUS/S2_SR_HARMONIZED')      .filterBounds(aoi)      .filterDate('2025-10-01', '2026-04-01')      .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 10))      .median())
# NDVI - vegetation density (lower = more suitable for solar)ndvi = s2.normalizedDifference(['B8', 'B4']).rename('ndvi')veg_penalty = ndvi.multiply(100).rename('veg_penalty')
# SRTM terrain slope and aspectdem = ee.Image('USGS/SRTMGL1_003')terrain = ee.Terrain.products(dem)slope = terrain.select('slope').rename('slope_deg')aspect = terrain.select('aspect').rename('aspect_deg')
# Slope penalty: sites > 5 deg lose suitability rapidlyslope_penalty = slope.pow(1.5).rename('slope_penalty')
# South-facing aspect score for southern hemisphere (180 deg = ideal)aspect_score = aspect.subtract(180).abs().subtract(180).abs()aspect_score = ee.Image(100).subtract(aspect_score.divide(1.8)).rename('aspect_score')
# Composite suitability index (0-100)suitability = (ee.Image(100)               .subtract(veg_penalty.multiply(0.3))               .subtract(slope_penalty.multiply(2))               .add(aspect_score.multiply(0.2))               .clamp(0, 100)               .rename('suitability'))
stats = suitability.reduceRegion(    reducer=ee.Reducer.mean().combine(ee.Reducer.percentile([25,75]), sharedInputs=True),    geometry=aoi, scale=30, maxPixels=1e9).getInfo()
print(f"Mean suitability: {stats['suitability_mean']:.1f}/100")print(f"P25 suitability: {stats['suitability_p25']:.1f}/100")print(f"P75 suitability: {stats['suitability_p75']:.1f}/100")

output/solar_feasibility_report.mdOutput report